© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 11109
    Prev
    Next
    INDEX
    Explanations

    volume control settings, power button

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mass
    -0.20
    æ´¹
    -0.20
     Harness
    -0.20
    é¦Ĩ
    -0.20
    ida
    -0.19
    館
    -0.18
    asia
    -0.18
    èıī
    -0.18
     massa
    -0.18
    uld
    -0.17
    POSITIVE LOGITS
    коÑģ
    0.21
    档次
    0.20
    swift
    0.20
    ync
    0.20
    çĶŁäº§æĢ»
    0.20
    æĹģ
    0.19
    æģ¯
    0.19
    广æĴŃ
    0.19
    éĿĻ
    0.19
    åıĺåĮĸ
    0.19
    Activations Density 0.013%

    No Known Activations